© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20781
    Prev
    Next
    INDEX
    Explanations

    tell you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    èĩªçĦ¶èĢĮ
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.09
    ier
    -0.08
    è¿Ļç§įæĸ¹æ³ķ
    -0.08
    å¹Ķ
    -0.08
    æĸ°åĮº
    -0.08
    нÑĭми
    -0.08
    è¡·
    -0.08
    å¤ĸåľ°
    -0.08
    POSITIVE LOGITS
    ç»ĻæĪij们
    0.21
    ç»Ļä½ł
    0.21
     us
    0.18
    ç»ĻæĪij
    0.17
     вам
    0.17
    ç»Ļä»ĸ
    0.17
     емÑĥ
    0.16
     мне
    0.16
    ç»ĻæĤ¨
    0.16
    åijĬè¯īæĪij们
    0.15
    Activations Density 0.212%

    No Known Activations